Improve provider reliability and usage visibility

crates/galaxy_agent_core/src/provider_run.rs

@@ -502,6 +502,10 @@ impl ProviderRun {
         self.model_retries
     }
 
+    pub fn max_model_retries_per_turn(&self) -> u32 {
+        self.limits.max_model_retries_per_turn
+    }
+
     pub fn is_terminal(&self) -> bool {
         matches!(
             self.state,
@@ -665,20 +669,20 @@ impl ProviderRun {
             }
             ProviderRunState::Failed { failure } => match failure.kind {
                 ProviderRunFailureKind::ModelCall
-                    if !failure
+                    if failure
                         .source
                         .as_ref()
-                        .is_some_and(|source| !source.recoverable) =>
+                        .is_none_or(|source| source.recoverable) =>
                 {
                     return Err(invalid(
                         "model-call failure lacks a non-recoverable source".to_string(),
                     ));
                 }
                 ProviderRunFailureKind::RetryLimitExceeded
-                    if !failure
+                    if failure
                         .source
                         .as_ref()
-                        .is_some_and(|source| source.recoverable) =>
+                        .is_none_or(|source| !source.recoverable) =>
                 {
                     return Err(invalid(
                         "retry-limit failure lacks a recoverable source".to_string(),

crates/galaxy_agent_core/src/types.rs

@@ -223,15 +223,21 @@ impl ToolEvent {
 
 #[derive(Clone, Debug, Default, PartialEq, Eq, Serialize, Deserialize)]
 pub struct Usage {
+    /// Input tokens not served by or written to a provider prompt cache.
     pub input_tokens: u64,
     pub output_tokens: u64,
+    /// Input tokens served from the provider prompt cache.
     pub cached_input_tokens: u64,
+    /// Input tokens written to the provider prompt cache.
     pub cache_creation_input_tokens: u64,
 }
 
 impl Usage {
     pub fn total_tokens(&self) -> u64 {
-        self.input_tokens.saturating_add(self.output_tokens)
+        self.input_tokens
+            .saturating_add(self.cached_input_tokens)
+            .saturating_add(self.cache_creation_input_tokens)
+            .saturating_add(self.output_tokens)
     }
 }
 
@@ -268,6 +274,9 @@ pub enum AgentEvent {
     TurnStarted {
         runtime_request_id: String,
     },
+    /// A transport heartbeat proving that the current model stream is still connected.
+    /// Consumers should use this to refresh idle timeouts without rendering output.
+    KeepAlive,
     TextDelta {
         text: String,
     },

crates/galaxy_agent_core/src/types_tests.rs

@@ -26,9 +26,9 @@ fn truncates_large_tool_results_for_provider_request() {
 }
 
 #[test]
-fn usage_total_excludes_cached_breakdown_to_avoid_double_counting() {
+fn usage_total_combines_disjoint_cache_and_miss_buckets() {
     let usage = Usage {
-        input_tokens: 100,
+        input_tokens: 10,
         output_tokens: 25,
         cached_input_tokens: 80,
         cache_creation_input_tokens: 10,